{
  "id": 18010,
  "url": "https://arxiv.org/abs/2608.09447v1",
  "title": "WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training",
  "summary": "On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The same feedback loop can nevertheless be unstable: each update changes both the policy and the states on which the next update is computed. We introduce WDL-OPD, a mixture-constrained co-training method with two trainable policies. An anchor policy generates every rollout, an auxiliary policy evaluates the same visited sta",
  "authors": "Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou et al.",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T11:22:53.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18010",
  "original_url": "https://arxiv.org/abs/2608.09447v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}